|
|
|
@ -2,12 +2,12 @@ |
|
|
|
|
<!---------------------------------------------------------------------------- |
|
|
|
|
A frontal cat face detector using the full set of Haar features, i.e. |
|
|
|
|
horizontal, vertical, and diagonal features. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Contributed by Joseph Howse (josephhowse@nummist.com). |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
More information can be found in the following publications and |
|
|
|
|
presentations: |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Joseph Howse. OpenCV for Secret Agents (book). Packt Publishing, January |
|
|
|
|
2015. |
|
|
|
|
Joseph Howse. "Training Detectors and Recognizers in Python and OpenCV" |
|
|
|
@ -16,21 +16,21 @@ |
|
|
|
|
Joseph Howse. "Training Intelligent Camera Systems with Python and OpenCV" |
|
|
|
|
(webcast). O’Reilly Media. June 17, 2014. |
|
|
|
|
http://www.oreilly.com/pub/e/3077 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Build scripts and demo applications can be found in the following repository: |
|
|
|
|
https://bitbucket.org/Joe_Howse/angora-blue |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
KNOWN LIMITATIONS: |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Sometimes, the detector mistakenly thinks that a human face is a cat face. In |
|
|
|
|
situations where either a human or a cat might be encountered, use both a |
|
|
|
|
human face detector and a cat face detector. Then, if a detected human face |
|
|
|
|
and a detected cat face intersect, reject the cat face. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
An upright subject is assumed. In situations where the cat's face might be |
|
|
|
|
sideways or upside down (e.g. the cat is rolling over), try various rotations |
|
|
|
|
of the input image. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
////////////////////////////////////////////////////////////////////////// |
|
|
|
|
| Contributors License Agreement |
|
|
|
|
| IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING. |
|
|
|
|